In this work, we investigate into the performance of mainstream neural generative models on the very task of swapping faces. We have experimented on CVAE, CGAN, CVAE-GAN, and conditioned diffusion models. Existing finely trained models have already managed to produce fake faces (Facke) indistinguishable to the naked eye as well as achieve high objective metrics. We perform a comparison among them and analyze their pros and cons. Furthermore, we proposed some promising tricks though they do not apply to this task.
@article{arxiv.2206.11203,
title = {Facke: a Survey on Generative Models for Face Swapping},
author = {Wei Jiang and Wentao Dong},
journal= {arXiv preprint arXiv:2206.11203},
year = {2022}
}